© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 13282
    Prev
    Next
    INDEX
    Explanations

    some/one/parts/areas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     anything
    -0.08
    igny
    -0.07
    gle
    -0.07
    chand
    -0.07
    çļĦä¸Ģ家
    -0.07
     enige
    -0.07
    |#
    -0.07
    é¼ĵèĪŀ
    -0.06
    åĬłåħ³æ³¨
    -0.06
    ring
    -0.06
    POSITIVE LOGITS
     portions
    0.10
    æĺİæĺİæĺ¯
    0.09
     particular
    0.09
     portion
    0.09
    /all
    0.08
    æĪĸå¤ļ
    0.08
    éĥ¨ä»½
    0.08
    æĺİæĺİ
    0.07
    æĺ¯å¾Īéĩįè¦ģçļĦ
    0.07
    ä¸įèµ·
    0.07
    Activations Density 0.185%

    No Known Activations